Skip to main content
Fig. 2 | BMC Nephrology

Fig. 2

From: Enhancing individual glomerular filtration rate assessment: can we trust the equation? Development and validation of machine learning models to assess the trustworthiness of estimated GFR compared to measured GFR

Fig. 2

Performance of the random forest model in external validation for the P30, P20 and P10 criteria. The probability thresholds used to evaluate the model’s performance metrics were 0.80 for the P30 criteria, 0.65 for the P20 criteria, and 0.45 for the P10 criteria. AUC: area under the curve; Acc: accuracy; Se: sensitivity; Sp: specificity; PPV: Predictive positive value; NPV: Negative predictive value

Back to article page

BMC Nephrology

ISSN: 1471-2369

Contact us